Protein design using structure prediction models such as AlphaFold2 has shown remarkable success, but existing approaches like relaxed sequence optimization (RSO) rely on single-path gradient descent and ignore sequence-space constraints, limiting diversity and designability. We introduce Relaxed Sequence Sampling (RSS), a Markov chain Monte Carlo (MCMC) framework that integrates structural and evolutionary information for protein design. RSS operates in continuous logit space, combining gradient-guided exploration with protein language model-informed jumps. Its energy function couples AlphaFold2-derived structural objectives with ESM2-derived sequence priors, balancing accuracy and biological plausibility. In an in silico protein binder design task, RSS produces 5$\times$ more designable structures and 2-3$\times$ greater structural diversity than RSO baselines, at equal computational cost. These results highlight RSS as a principled approach for efficiently exploring the protein design landscape.
Relaxed Leverage Sampling for Low-rank Matrix Completion
Xerox Research Center India(施乐印度研究中心)
我们考虑的问题,通过标准的核范数最小化框架的任何$m\times n$矩阵的秩$\varrho$从少量的观察到的条目的精确恢复。这种低秩矩阵具有自由度$(m+n)\varrho - \varrho^2$。我们发现,任何任意低秩矩阵可以完全恢复从一个$Θ\left(((m+n)\varrho - \varrho^2)\log^2(m+n)\right)$随机采样的条目,从而匹配所需的条目数的下限(在自由度方面),与一个额外的因素$O(\log^2(m+n))$。为了达到样本大小的这个界限,我们观察每个条目的概率与相应的行和列杠杆分数之和成比例,减去它们的乘积。我们表明,这种放宽抽样概率(与Chen et al,2014中的杠杆分数之和相反)可以为我们提供$O(\varrho^2\log^2(m+n))$附加改进Chen et al,2014获得的(最知名的)样本量,用于核范数最小化。实际数据的实验证实了理论上的样本容量的改善。此外,$(a)$非相干矩阵(具有受限的杠杆分数)和仅具有一个行或列空间的$(b)$矩阵的精确恢复可以使用我们的放松杠杆分数采样,经由核范数最小化,而无需先验地知道杠杆分数。在这种情况下,我们也可以提高样本量。
Sampling at intermediate temperatures is optimal for training large language models in protein structure prediction
Department of Physics, via Celoria 16, 20133 Milano, Italy(米兰大学物理系);Department of Physics and INFN, via Celoria 16, 20133 Milano, Italy(米兰大学物理系与意大利国家核物理研究院)
Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets
Tsinghua University, Beijing, China(清华大学);HeliXon Limited, Beijing, China(HeliXon有限公司);Department of Computer Science, University of Illinois at Urbana-Champaign, Champaign, USA(伊利诺伊大学厄巴纳-香槟分校计算机科学系);Westlake University, Hangzhou, China(西湖大学);Department of Electronic Engineering, Tsinghua University, Beijing, China(清华大学电子工程系);Institute for AI Industry Research, Tsinghua University, Beijing, China(清华大学人工智能产业研究院)
Improving AlphaFlow for Efficient Protein Ensembles Generation
The Chinese University of Hong Kong(香港中文大学);Shanghai Jiao Tong University School of Medicine(上海交通大学医学院);Xi’an Jiaotong University(西安交通大学);Shanghai Institute of Materia Medica, Chinese Academy of Sciences(中国科学院上海药物研究所)
Learning conformational ensembles of proteins based on backbone geometry
Max Planck Institute for Polymer Research(马克斯·普朗克聚合物研究所);Heidelberg Institute for Theoretical Studies(海德堡理论研究所);IWR, Heidelberg University(海德堡大学IWR中心);SciLifeLab and DBB at Stockholm University(斯德哥尔摩大学SciLifeLab和DBB中心);Karlsruhe Institute of Technology(卡尔斯鲁厄技术大学)